# FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures

Source: [FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures](<https://www.sota2.com/research/paper/68fa74301e209131cea604fd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:08.145Z

Authors: Hao Lu, Wenze Liu, Hongtao Fu, Zhiguo Cao

Published: 2024-07-18T13:32:36.000Z

## Abstract

The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: i) considering both the encoder and decoder feature in upsampling kernel generation; ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator; and iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://github.com/poppinace/fade

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.13500>)

[PDF](<https://arxiv.org/pdf/2407.13500.pdf>)
